摘要
针对传统的搜索引擎对于自然语言理解方面存在的问题,文章研究了一种新的基于自然语言处理技术和相似度计算的智能搜索引擎的模型.其核心技术是基于自然语言处理的中文分词技术、语义相似度和对立度等理论,将这些概念理论结合起来,从用户习惯的思考角度,结合DotLucene开源全文搜索引擎建立一个智能的搜索引擎.研究表明,该模型在对已经收录的文档有着86.1%的查准率.该智能搜索引擎较好的对查询语句的实现了理解,能够对用户的提问做出正确的回答.
To deal with the problems of traditional search engine in understanding natural language,this article proposes a new intelligent search engine model which is based on the natural language processing and similarity calculation.Its core technology is Chinese word segmentation technique based on natural language processing,semantic similarity and contrary degree.Thinking from the users' view,the model combines DotLucene with those concepts.The precision of the intelligent search engine is about 86.1%.The intelligent search engine can understand the natural languages to query and offer the right answer to users.
出处
《昆明理工大学学报(理工版)》
北大核心
2010年第4期76-79,88,共5页
Journal of Kunming University of Science and Technology(Natural Science Edition)
基金
广西自然科学基金资助项目(桂科自0991254)